Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 19043
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal matters or policies

    oai_token-act-pair · gpt-3.5-turbo

    references to legal terminology and discussions surrounding legal cases or frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isphere
    -0.54
    EngineDebug
    -0.53
    ãĥ´ãĤ¡
    -0.52
    ب
    -0.51
    ãĥĸ
    -0.50
    Ö
    -0.49
    ÙĦ
    -0.49
    ignt
    -0.49
    idth
    -0.48
    ãĤ¨ãĥ«
    -0.48
    POSITIVE LOGITS
     latter
    0.51
     unfortunate
    0.51
     discomfort
    0.49
    cing
    0.47
     sadd
    0.45
     shaming
    0.45
    entimes
    0.44
     Cards
    0.44
     contrast
    0.43
     AAP
    0.43
    Activations Density 1.209%

    No Known Activations